Transactions on Mass-Data Analysis of Images and Signals P-ISSN1868-6451, E-ISSN 2509-9353, ISBN 978-3-942952-80-4
Volume 11 - Number 1 - September 2020 - Page 27-53
Expert Opinion on Automatic Image Analysis for Cellular and Molecular Biology and Drug Discovery
Petra Perner
FutureLab Artificial Intelligence_IBaI_2, Radeberg, Germany
Abstract
In the rapidly expanding fields of cellular and molecular biology, fluorescence illumination and observation is becoming one of the techniques of choice to study the localization and dynamics of proteins, organelles, and other cellular compartments, as well as a tracer of intracellular protein trafficking. In drug discovery cell-based assays are used to study the impact of the drug under development. In both applications microscopic cell images are taken for these studies. The automatic analysis of these images and signals in medicine, biotechnology, and chemistry is a challenging and demanding field. In this paper we present our newly developed methods and techniques for the analysis of microscopic cell images. We present methods for static 2-D image analysis and dynamic 3-D image analysis. We start with a description of the challenges and requirements to the systems. Then we move further with a description of any processing unit in the full image analysis chain. We start with image segmentation followed by feature extraction, image mining, and image interpretation. Our new method for meta learning of image segmentation is described. Automatic and symbolic feature extraction is described as well as our novel texture descriptor that is effective for the description of the texture on cells. The image mining methods for learning the interpretation knowledge is described by a supervised method based on decision tree induction and an unsupervised method by conceptual clustering. We give an overview of our novel method for live cell tracking. We show on results the extraordinary performance of the methods. At the end of the paper we give a summary of our expert opinion on microscopic image analysis for cellular and molecular biology. Finally, we summarize our work in the conclusion section.
Keywords: Microscopic Image Analysis, Image Analysis and Interpretation, High-Content Analysis of Images HCA, Automation and Standardization of Visual Inspection Tasks, Image-Mining,
Download Paper
(638 KB)